A Vision-Based System for a UGV to Handle a Road Intersection

Abstract

We propose a real-time computer vision system that enables a UGV to safely cross urban road-intersections. Specifically, when the UGV approaches the stop sign at a 4-way intersection, it must be aware of the vehicles at the other three roads and adhere to traffic rules by waiting for its turn to proceed. The proposed solution consists of three main components: a vehicle detector, a tracker, and a finite-state-machine to model the traffic. We use an OT-MACH filter to detect the leading vehicle in each of three camera-views of the corresponding roads. Then, we track the vehicles using an edge-enhanced dynamic correlation tracker, which estimates the current and next positions, velocities, and accelerations of the vehicles. Finally, the finite-state-machine describes the traffic in each road with one of four possible states (i.e. No Vehicle Waiting, Arriving, Waiting, and Passing), and signals an autopilot system when it is safe to pass the intersection. We provide the results from an actual intersection with real traffic to demonstrate that the UGV is able to automatically navigate the intersection using the proposed system. Copyright © 2007, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.